{ "info": { "author": "", "author_email": "", "bugtrack_url": null, "classifiers": [ "Intended Audience :: Developers", "Intended Audience :: Science/Research", "License :: OSI Approved", "Operating System :: MacOS", "Operating System :: Microsoft :: Windows", "Operating System :: POSIX", "Operating System :: Unix", "Programming Language :: Python", "Programming Language :: Python :: 3.6", "Topic :: Scientific/Engineering", "Topic :: Software Development" ], "description": ".. image:: https://travis-ci.com/uea-machine-learning/sktime-dl.svg?branch=master\n :target: https://travis-ci.com/uea-machine-learning/sktime-dl\n.. image:: https://badge.fury.io/py/sktime-dl.svg\n :target: https://badge.fury.io/py/sktime-dl\n\nsktime-dl\n=========\nAn extension package for deep learning with Keras for `sktime `__, a `scikit-learn `__ compatible Python toolbox for learning with time series and panel data. \n\nThe package is under active development. Currently, classification models based off the the networks in `dl-4-tsc `__ have been implemented, as well as an example of a tuned network for future development. \n\nInstallation\n------------\nThis package uses the base sktime as a dependency. Follow the `original instructions `__ to install this. \n\nFor the deep-learning part of sktime-dl, you need:\n\n- `Keras `__\n- `keras-contrib `__ \n- and a compatible backend for Keras, one of \n\n - `tensorflow `__ (confirmed working, v1.8.0)\n - `theano `__ (untested)\n - `CNTK `__ (untested)\n\nIf you want to run the networks on a GPU, `CUDNN `__ is also required to be able to utilise your GPU. \n\nFor windows users, we recommend following `this `__ (unaffiliated) guide.\n\nFor linux users, all of these points should hopefully be relatively straight forward via simple pip-commands and conversions from the previous link.\n\nFor mac users, I am unfortunately unsure of the best processes for installing these. If you have links to a tested and up-to-date guide, let us know (@James-Large).\n\nOverview\n--------\n\nA repository for off-the-shelf networks\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\nThe aim is to define Keras networks able to be directly used within sktime and its pipelining and strategy tools, and by extension scikit-learn, for use in applications and research. Overtime, we wish to interface or reimplement networks from the literature in the context of time series analysis.\n\nCurrently, we interface with a number of networks for time series classification in particular. \n\ndl-4-tsc interfacing\n~~~~~~~~~~~~~~~~~~~~\n\nThis toolset currently serves as an interface to `dl-4-tsc `__, and implements the following network archtiectures: \n\n- Time convolutional neural network (CNN)\n- Encoder (Encoder)\n- Fully convolutional neural network (FCNN)\n- Multi channel deep convolutional neural network (MCDCNN)\n- Multi-scale convolutional neural network (MCNN)\n- Multi layer perceptron (MLP)\n- Residual network (resnet)\n- Time Le-Net (tlenet)\n- Time warping invariant echo state network (twiesn)\n\n\nDocumentation\n-------------\nThe full API documentation to the base sktime and an introduction can be found `here `__.\nTutorial notebooks for currently stable functionality are in the `examples `__ folder.\n\nDocumentation for sktime-dl shall be produced in due course.\n\nContributors\n------------\nFormer and current active contributors are as follows.\n\nsktime-dl\n~~~~~~~~~\n\nJames Large (@James-Large), Aaron Bostrom (@ABostrom), Hassan Ismail Fawaz (@hfawaz), Markus L\u00f6ning (@mloning)\n\nsktime\n~~~~~~\n\nProject management: Jason Lines (@jasonlines), Franz Kir\u00e1ly (@fkiraly)\n\nDesign: Anthony Bagnall(@TonyBagnall), Sajaysurya Ganesh (@sajaysurya), Jason Lines (@jasonlines), Viktor Kazakov (@viktorkaz), Franz Kir\u00e1ly (@fkiraly), Markus L\u00f6ning (@mloning)\n\nCoding: Sajaysurya Ganesh (@sajaysurya), Bagnall(@TonyBagnall), Jason Lines (@jasonlines), George Oastler (@goastler), Viktor Kazakov (@viktorkaz), Markus L\u00f6ning (@mloning)\n\nWe are actively looking for contributors. Please contact @fkiraly or @jasonlines for volunteering or information on paid opportunities, or simply raise an issue in the tracker.\n\n\n", "description_content_type": "", "docs_url": null, "download_url": "https://pypi.org/project/sktime-dl/#files", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/uea-machine-learning/sktime-dl", "keywords": "", "license": "BSD-3-Clause", "maintainer": "F. Kir\u00e1ly", "maintainer_email": "fkiraly@turing.ac.uk", "name": "sktime-dl", "package_url": "https://pypi.org/project/sktime-dl/", "platform": "", "project_url": "https://pypi.org/project/sktime-dl/", "project_urls": { "Download": "https://pypi.org/project/sktime-dl/#files", "Homepage": "https://github.com/uea-machine-learning/sktime-dl" }, "release_url": "https://pypi.org/project/sktime-dl/0.1.0/", "requires_dist": [ "sktime (>=0.2.0)", "keras (>=2.2.4)", "tensorflow (>=1.8.0)", "sphinx ; extra == 'docs'", "sphinx-gallery ; extra == 'docs'", "sphinx-rtd-theme ; extra == 'docs'", "numpydoc ; extra == 'docs'", "matplotlib ; extra == 'docs'", "pytest ; extra == 'tests'", "pytest-cov ; extra == 'tests'" ], "requires_python": "", "summary": "Deep learning extension package for sktime, a scikit-learn compatible toolbox for learning with time series data", "version": "0.1.0" }, "last_serial": 5608297, "releases": { "0.1.0": [ { "comment_text": "", "digests": { "md5": "d3493534546d2590502ca93cb295960e", "sha256": "f4309ceed1321bf940a9e02571d49eacb680467605506ad7ae8c9bb617161e7c" }, "downloads": -1, "filename": "sktime_dl-0.1.0-py3-none-any.whl", "has_sig": false, "md5_digest": "d3493534546d2590502ca93cb295960e", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 33379, "upload_time": "2019-07-30T15:24:24", "url": "https://files.pythonhosted.org/packages/3a/26/b2d4ed064b0b67adfcbeb0b9cc92672c7aa841e70da15ecae18dd6eb02b8/sktime_dl-0.1.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "961210762f3e928f986ab5d10600cd62", "sha256": "8d3ae37a98163f31fc836ef5c3cd54a1341dd7ee74812409cbdf610e2d8c6d39" }, "downloads": -1, "filename": "sktime-dl-0.1.0.tar.gz", "has_sig": false, "md5_digest": "961210762f3e928f986ab5d10600cd62", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 22408, "upload_time": "2019-07-30T15:24:27", "url": "https://files.pythonhosted.org/packages/e2/c6/487febeea54adfe56467948a13bc7d87f8ddec4b275b4837c84a88bb55ad/sktime-dl-0.1.0.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "d3493534546d2590502ca93cb295960e", "sha256": "f4309ceed1321bf940a9e02571d49eacb680467605506ad7ae8c9bb617161e7c" }, "downloads": -1, "filename": "sktime_dl-0.1.0-py3-none-any.whl", "has_sig": false, "md5_digest": "d3493534546d2590502ca93cb295960e", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 33379, "upload_time": "2019-07-30T15:24:24", "url": "https://files.pythonhosted.org/packages/3a/26/b2d4ed064b0b67adfcbeb0b9cc92672c7aa841e70da15ecae18dd6eb02b8/sktime_dl-0.1.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "961210762f3e928f986ab5d10600cd62", "sha256": "8d3ae37a98163f31fc836ef5c3cd54a1341dd7ee74812409cbdf610e2d8c6d39" }, "downloads": -1, "filename": "sktime-dl-0.1.0.tar.gz", "has_sig": false, "md5_digest": "961210762f3e928f986ab5d10600cd62", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 22408, "upload_time": "2019-07-30T15:24:27", "url": "https://files.pythonhosted.org/packages/e2/c6/487febeea54adfe56467948a13bc7d87f8ddec4b275b4837c84a88bb55ad/sktime-dl-0.1.0.tar.gz" } ] }